def newickToTree(s):
from newick import parse_tree #http://www.brics.dk/~mailund/newick.html
t = parse_tree(s)
v = NewickVisitor()
t.dfs_traverse(v)
A = v.getAdjMap()
return A
def newickToTree(s):
from newick import parse_tree #http://www.brics.dk/~mailund/newick.html
t = parse_tree(s)
v = NewickVisitor()
t.dfs_traverse(v)
A = v.getAdjMap()
return A
def parse_tree(newick_str):
tree = None
try:
tree = newick.parse_tree(newick_str)
except newick.lexer.LexerError as e:
raise PhyloException("Error parsing tree")
return tree
def parse_tree(treestring):
"""Wrapper on the newick.parse_tree to add parent edges and a leaf lookup.
"""
my_tree = newick.parse_tree(treestring)
newick.tree.add_parent_links(my_tree)
return my_tree
def parse_tree(treestring):
"""Wrapper on the newick.parse_tree to add parent edges and a leaf lookup.
"""
my_tree = newick.parse_tree(treestring)
newick.tree.add_parent_links(my_tree)
return my_tree
def newick_tree_to_pygraph(string):
g = graph()
l = [0]
def sub(tree):
if isinstance(tree, newick.tree.Leaf):
# if it's just a label
g.add_node(tree.identifier)
return tree.identifier
else:
# it's a tree and has edges
l[0] += 1
my_l = l[0]
g.add_node(my_l)
for i,e in enumerate(tree.get_edges()):
child = sub(e[0])
g.add_edge((my_l, child))
return my_l
t = newick.parse_tree(string)
sub(t)
return g
def main(organism, gene_id):
write_fasta = False
cache_dir = os.path.join(os.getcwd(), "cache")
ensembl_rest = EnsemblComparaRest(cache_dir)
orthologs = ensembl_rest.orthologs(organism, gene_id)
compara_tree = ensembl_rest.compara_tree(organism, gene_id)
compara_tree = '(' + compara_tree[:-1] + ');'
tree_rec = newick.parse_tree(compara_tree.strip())
d_vis = DistanceVisitor()
tree_rec.dfs_traverse(d_vis)
tree_proteins = [l.identifier for l in tree_rec.leaves]
orthologs = [(organism, gene_id)] + orthologs
out_recs = []
root_id = None
all_items = []
for o_organism, o_id in orthologs:
transcripts = ensembl_rest.transcripts(o_organism, o_id)
tx, p = [(tx, p) for (tx, p) in transcripts if p in
tree_proteins][0]
cur_item = EnsemblComparaTranscript(o_organism, o_id, tx, p)
if root_id is None:
root_id = p
cur_item.distance = networkx.dijkstra_path_length(d_vis.graph,
"'%s'" % root_id, "'%s'" % p)
#print o_organism, o_id, p
cur_item.domains = ensembl_rest.protein_domains(o_organism, o_id,
tx)
cur_item.statistics = ensembl_rest.protein_stats(o_organism, o_id,
tx)
all_items.append(cur_item)
if write_fasta:
out_rec = ensembl_rest.protein_fasta(o_organism, o_id,
tx)
out_rec.id = o_id
out_rec.description = o_organism
out_recs.append(out_rec)
if len(out_recs) > 0:
with open("%s_%s_orthologs.txt" % (organism, gene_id), "w") as \
out_handle:
SeqIO.write(out_recs, out_handle, "fasta")
analyze_comparative_set(all_items)
def main(organism, gene_id):
write_fasta = False
cache_dir = os.path.join(os.getcwd(), "cache")
ensembl_rest = EnsemblComparaRest(cache_dir)
orthologs = ensembl_rest.orthologs(organism, gene_id)
compara_tree = ensembl_rest.compara_tree(organism, gene_id)
compara_tree = '(' + compara_tree[:-1] + ');'
tree_rec = newick.parse_tree(compara_tree.strip())
d_vis = DistanceVisitor()
tree_rec.dfs_traverse(d_vis)
tree_proteins = [l.identifier for l in tree_rec.leaves]
orthologs = [(organism, gene_id)] + orthologs
out_recs = []
root_id = None
all_items = []
for o_organism, o_id in orthologs:
transcripts = ensembl_rest.transcripts(o_organism, o_id)
tx, p = [(tx, p) for (tx, p) in transcripts if p in tree_proteins][0]
cur_item = EnsemblComparaTranscript(o_organism, o_id, tx, p)
if root_id is None:
root_id = p
cur_item.distance = networkx.dijkstra_path_length(
d_vis.graph, "'%s'" % root_id, "'%s'" % p)
#print o_organism, o_id, p
cur_item.domains = ensembl_rest.protein_domains(o_organism, o_id, tx)
cur_item.statistics = ensembl_rest.protein_stats(o_organism, o_id, tx)
all_items.append(cur_item)
if write_fasta:
out_rec = ensembl_rest.protein_fasta(o_organism, o_id, tx)
out_rec.id = o_id
out_rec.description = o_organism
out_recs.append(out_rec)
if len(out_recs) > 0:
with open("%s_%s_orthologs.txt" % (organism, gene_id), "w") as \
out_handle:
SeqIO.write(out_recs, out_handle, "fasta")
analyze_comparative_set(all_items)
import sys
from newick import parse_tree
intree=sys.argv[1]
infile=open(intree)
text=infile.read()
#file=open("/home/junm/baylor/fulldata/NONPQ_rep_set_aligned.tre")
print intree
outtree=intree.replace('.tre','.parsed.tre')
print outtree
outfile=open(outtree,"w")
outfile.write(str(parse_tree(text)))
